You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@@ -111,7 +111,7 @@ During training, we take a batch of medical questions and their corresponding me
![DoctorBert](https://i.imgur.com/Lpjjcvk.jpg)
These embeddings are then inputted into a FCNN layer. There are separate FCNN layers for both the question and answer embeddings.
These embeddings are then inputted into a FCNN layer. There are separate FCNN layers for both the question and answer embeddings. To recap, we use the same weights in the Bert layer, but the questions and answers each have their own seperate FCNN layer.